Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks
作者： Kurt Hornik , Maxwell Stinchcombe , Halbert White
DOI: 10.1016/0893-6080(90)90005-6
关键词:
摘要: We give conditions ensuring that multilayer feedforward networks with as few as a single hidden layer and an appropriately smooth hidden layer activation function are capable of arbitrarily accurate approximation to an arbitrary function and its derivatives. In fact, these networks can approximate functions that are not differentiable in the classical sense, but possess only a generalized derivative, as is the case for certain piecewise differentiable functions. The conditions imposed on the hidden layer activation function are relatively mild; …
acm.org
elsevier.com
sci-hub.se 参考文章(17)
Alois Kutner, Anna-Margarete Sändig, Some applications of weighted Sobolev spaces Teubner. ,(1987) , 10.1007/978-3-663-11385-0
Laurent Schwartz, Théorie des distributions ,(1966)
Ibrahim Elbadawi, A. Ronald Gallant, Geraldo Souza, An elasticity can be estimated consistently without a priori knowledge of functional form Econometrica. ,vol. 51, pp. 1731- 1751 ,(1983) , 10.2307/1912114
Alois Kufner, Weighted Sobolev Spaces ,(1985)
Harry Dym, Henry P. McKean, Fourier series and integrals ,(1972)
Irie, Miyake, Capabilities of three-layered perceptrons IEEE 1988 International Conference on Neural Networks. pp. 641- 648 ,(1988) , 10.1109/ICNN.1988.23901
Ken-Ichi Funahashi, On the approximate realization of continuous mappings by neural networks Neural Networks. ,vol. 2, pp. 183- 192 ,(1989) , 10.1016/0893-6080(89)90003-8
Ralph E. Showalter, Hilbert Space Methods for Partial Differential Equations ,(1979)
Gilstrap, Dominy, A general explanation and interrogation system for neural networks international joint conference on neural network. pp. 594- ,(1989) , 10.1109/IJCNN.1989.118383
Aman Ullah, Non-parametric estimation of econometric functionals Canadian Journal of Economics. ,vol. 17, pp. 625- 658 ,(1988) , 10.2307/135443